Latent Preserving Generative Adversarial Network for Imbalance classification

TL;DR

This paper introduces a novel deep generative adversarial network that effectively addresses high-dimensional class imbalance in classification tasks by preserving latent space and leveraging adversarial training.

Contribution

It proposes a domain-constraint autoencoder within a GAN framework to improve minority class classification in high-dimensional imbalanced data.

Findings

Outperforms state-of-the-art methods on three imbalanced datasets.

Effective in high-dimensional classification problems.

Code available for reproducibility.

Abstract

Many real-world classification problems have imbalanced frequency of class labels; a well-known issue known as the "class imbalance" problem. Classic classification algorithms tend to be biased towards the majority class, leaving the classifier vulnerable to misclassification of the minority class. While the literature is rich with methods to fix this problem, as the dimensionality of the problem increases, many of these methods do not scale-up and the cost of running them become prohibitive. In this paper, we present an end-to-end deep generative classifier. We propose a domain-constraint autoencoder to preserve the latent-space as prior for a generator, which is then used to play an adversarial game with two other deep networks, a discriminator and a classifier. Extensive experiments are carried out on three different multi-class imbalanced problems and a comparison with state-of-the-art methods. Experimental results confirmed the superiority of our method over popular algorithms in handling high-dimensional imbalanced classification problems. Our code is available on https://github.com/TanmDL/SLPPL-GAN.